{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T23:08:54Z","timestamp":1778368134564,"version":"3.51.4"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032191045","type":"print"},{"value":"9783032191052","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-19105-2_40","type":"book-chapter","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:15:29Z","timestamp":1778364929000},"page":"577-590","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Concept-Based Approach to\u00a0Voice Disorder Detection"],"prefix":"10.1007","author":[{"given":"Davide","family":"Ghia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriele","family":"Ciravegna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alkis","family":"Koudounas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Fantini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erika","family":"Crosetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Succo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tania","family":"Cerquitelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"40_CR1","unstructured":"Alvarez-Melis, D., Jaakkola, T.S.: Towards robust interpretability with self-explaining neural networks (2018). https:\/\/arxiv.org\/abs\/1806.07538"},{"issue":"1","key":"40_CR2","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s41591-018-0240-2","volume":"25","author":"ZI Attia","year":"2019","unstructured":"Attia, Z.I., et al.: Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Nat. Med. 25(1), 70\u201374 (2019)","journal-title":"Nat. Med."},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Bhattacharyya, N.: The prevalence of voice problems among adults in the united states. The Laryngoscope (2014)","DOI":"10.1002\/lary.24740"},{"key":"40_CR4","unstructured":"Brunner, E., Eberhard, K., Gugatschka, M.: Prevalence of benign vocal fold lesions: long-term results from a single European institution. J. Voice (2023)"},{"key":"40_CR5","unstructured":"Chen, C., Li, O., Tao, A., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 32 (2019)"},{"key":"40_CR6","unstructured":"Ciravegna, G., et al.: Non-invasive ai-powered diagnostics: the case of voice-disorder detection-vision paper. In: Proceedings of the Workshops of the EDBT\/ICDT 2024 Joint Conference, vol. 3651. CEUR (2024)"},{"issue":"9","key":"40_CR7","doi-asserted-by":"publisher","first-page":"2118","DOI":"10.1002\/lary.24688","volume":"124","author":"SM Cohen","year":"2014","unstructured":"Cohen, S.M., Thomas, S., Roy, N., Kim, J., Courey, M.: Frequency and factors associated with use of videolaryngostroboscopy in voice disorder assessment. Laryngoscope 124(9), 2118\u20132124 (2014). https:\/\/doi.org\/10.1002\/lary.24688. epub 2014 May 7","journal-title":"Laryngoscope"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Cohen, S.M.: Self-reported impact of dysphonia in a primary care population: an epidemiological study. The Laryngoscope (2010)","DOI":"10.1002\/lary.21058"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature (2017)","DOI":"10.1038\/nature21056"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Fantini, M., et al.: The rapidly evolving scenario of acoustic voice analysis in otolaryngology. Cureus 16(11) (2024)","DOI":"10.7759\/cureus.73491"},{"key":"40_CR11","unstructured":"Gemini Team: Gemini: A family of highly capable multimodal models (2025). https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"40_CR12","unstructured":"Ghorbani, A., Wexler, J., Zou, J., Kim, B.: Towards automatic concept-based explanations (2019). https:\/\/arxiv.org\/abs\/1902.03129"},{"key":"40_CR13","unstructured":"Goyal, Y., Feder, A., Shalit, U., Kim, B.: Explaining classifiers with causal concept effect (CACE) (2020). https:\/\/arxiv.org\/abs\/1907.07165"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Gulshan, V., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama 316(22), 2402\u20132410 (2016)","DOI":"10.1001\/jama.2016.17216"},{"issue":"2","key":"40_CR15","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.jvoice.2020.11.026","volume":"37","author":"AL Hamdan","year":"2023","unstructured":"Hamdan, A.L., Ghanem, A., Natout, T.E., Khalifee, E.: Diagnostic yield of office-based laryngeal biopsy in patients with leukoplakia; a case study with review of the literature. J. Voice 37(2), 282\u2013286 (2023). https:\/\/doi.org\/10.1016\/j.jvoice.2020.11.026. epub 2021 Jan 28","journal-title":"J. Voice"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: self-supervised speech representation learning by masked prediction of hidden units (2021). https:\/\/arxiv.org\/abs\/2106.07447","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"40_CR17","doi-asserted-by":"publisher","unstructured":"Islam, R., Abdel-Raheem, E., Tarique, M.: Voice pathology detection using convolutional neural networks with electroglottographic (EGG) and speech signals. Comput. Methods Programs Biomed. Update 2, 100074 (2022). https:\/\/doi.org\/10.1016\/j.cmpbup.2022.100074, cC BY-NC-ND 4.0","DOI":"10.1016\/j.cmpbup.2022.100074"},{"key":"40_CR18","doi-asserted-by":"publisher","unstructured":"Jesus, L.M., Belo, I., Machado, J., Hall, A.: The advanced voice function assessment databases (AVFAD): tools for voice clinicians and speech research. In: Fernandes, F.D.M. (ed.) Advances in Speech-language Pathology, chap. 14. IntechOpen, Rijeka (2017). https:\/\/doi.org\/10.5772\/intechopen.69643","DOI":"10.5772\/intechopen.69643"},{"key":"40_CR19","unstructured":"Jiang, A.Q., et al.: Mistral 7b (2023). https:\/\/arxiv.org\/abs\/2310.06825"},{"issue":"2","key":"40_CR20","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/JSTSP.2019.2957988","volume":"14","author":"SR Kadiri","year":"2020","unstructured":"Kadiri, S.R., Alku, P.: Analysis and detection of pathological voice using glottal source features. IEEE J. Sel. Topics Signal Process. 14(2), 367\u2013379 (2020). https:\/\/doi.org\/10.1109\/JSTSP.2019.2957988","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Karabayir, I., Goldman, S.M., Pappu, S., Akbilgic, O.: Gradient boosting for Parkinson\u2019s disease diagnosis from voice recordings. BMC Med. Inf. Decis. Making (2020)","DOI":"10.21203\/rs.2.20727\/v3"},{"key":"40_CR22","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1044\/1058-0360(2008\/08-0017)","volume":"18","author":"G Kempster","year":"2009","unstructured":"Kempster, G., Gerratt, B., Verdolini Abbott, K., Barkmeier-Kraemer, J., Hillman, R.: Consensus auditory-perceptual evaluation of voice: development of a standardized clinical protocol. Am. J. Speech Lang. Pathol. 18, 124\u2013132 (2009). https:\/\/doi.org\/10.1044\/1058-0360(2008\/08-0017)","journal-title":"Am. J. Speech Lang. Pathol."},{"key":"40_CR23","unstructured":"Kim, B., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV) (2018). https:\/\/arxiv.org\/abs\/1711.11279"},{"key":"40_CR24","unstructured":"Kim, E., Jung, D., Park, S., Kim, S., Yoon, S.: Probabilistic concept bottleneck models (2023). https:\/\/arxiv.org\/abs\/2306.01574"},{"key":"40_CR25","unstructured":"Koh, P.W., et al.: Concept bottleneck models. In: Proceedings of the 37th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 119, pp. 5338\u20135352. PMLR (2020). https:\/\/proceedings.mlr.press\/v119\/koh20a.html"},{"key":"40_CR26","doi-asserted-by":"publisher","unstructured":"Koudounas, A., et al.: Voice disorder analysis: a transformer-based approach. In: Interspeech 2024, pp. 3040\u20133044. ISCA (2024). https:\/\/doi.org\/10.21437\/interspeech.2024-1122","DOI":"10.21437\/interspeech.2024-1122"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Koudounas, A., et al.: MVP: multi-source voice pathology detection. In: Proceedings of the Interspeech 2025 (2025)","DOI":"10.21437\/Interspeech.2025-1868"},{"key":"40_CR28","doi-asserted-by":"publisher","unstructured":"Koudounas, A., La Quatra, M., Siniscalchi, S.M., Baralis, E.: voc2vec: a foundation model for non-verbal vocalization. In: 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2025, pp. 1\u20135 (2025). https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10890672","DOI":"10.1109\/ICASSP49660.2025.10890672"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"La Quatra, M., Koudounas, A., Salerno, V.M., Siniscalchi, S.M.: Exploring generative error correction for dysarthric speech recognition. In: Proceedings of the Interspeech 2025 (2025)","DOI":"10.21437\/Interspeech.2025-1553"},{"key":"40_CR30","doi-asserted-by":"publisher","unstructured":"La Quatra, M., et al.: Benchmarking representations for speech, music, and acoustic events. In: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pp. 505\u2013509 (2024). https:\/\/doi.org\/10.1109\/ICASSPW62465.2024.10625960","DOI":"10.1109\/ICASSPW62465.2024.10625960"},{"key":"40_CR31","unstructured":"Liu, Q., Ciravegna, G., Koudounas, A., Cerquitelli, T., Baralis, E., et al.: Multimodal fusion techniques to enhance voice disorder diagnoses. In: CEUR Workshop Proceedings, vol. 3946. CEUR (2025)"},{"key":"40_CR32","doi-asserted-by":"publisher","unstructured":"Mersha, M., Lam, K., Wood, J., AlShami, A.K., Kalita, J.: Explainable artificial intelligence: a survey of needs, techniques, applications, and future direction. Neurocomputing 599, 128111 (2024). https:\/\/doi.org\/10.1016\/j.neucom.2024.128111","DOI":"10.1016\/j.neucom.2024.128111"},{"key":"40_CR33","unstructured":"Oikarinen, T., Das, S., Nguyen, L.M., Weng, T.W.: Label-free concept bottleneck models. arXiv preprint arXiv:2304.06129 (2023)"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Palaniappan, K., Lin, E.Y.T., Vogel, S.: Global regulatory frameworks for the use of artificial intelligence (AI) in the healthcare services sector. In: Healthcare, vol. 12, p. 562. MDPI (2024)","DOI":"10.3390\/healthcare12050562"},{"key":"40_CR35","doi-asserted-by":"crossref","unstructured":"Pastor, E., Koudounas, A., Attanasio, G., Hovy, D., Baralis, E.: Explaining speech classification models via word-level audio segments and paralinguistic features. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2221\u20132238 (2024)","DOI":"10.18653\/v1\/2024.eacl-long.136"},{"key":"40_CR36","doi-asserted-by":"publisher","unstructured":"Peng, X., Xu, H., Liu, J., et al.: Voice disorder classification using convolutional neural network based on deep transfer learning. Sci. Rep. 13, 7264 (2023). https:\/\/doi.org\/10.1038\/s41598-023-34461-9","DOI":"10.1038\/s41598-023-34461-9"},{"key":"40_CR37","doi-asserted-by":"publisher","unstructured":"Pietruszewska, W., et al.: Comparative analysis of high-speed videolaryngoscopy images and sound data simultaneously acquired from rigid and flexible laryngoscope: a pilot study. Sci. Rep. 11(1), 20480 (2021). https:\/\/doi.org\/10.1038\/s41598-021-99948-9","DOI":"10.1038\/s41598-021-99948-9"},{"key":"40_CR38","unstructured":"Poeta, E., Ciravegna, G., Pastor, E., Cerquitelli, T., Baralis, E.: Concept-based explainable artificial intelligence: a survey (2023). https:\/\/arxiv.org\/abs\/2312.12936"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Ribas, D., Pastor, M.A., Miguel, A., Mart\u00ednez, D., Ortega, A., Lleida, E.: Automatic voice disorder detection using self-supervised representations. IEEE Access (2023)","DOI":"10.1109\/ACCESS.2023.3243986"},{"key":"40_CR40","doi-asserted-by":"crossref","unstructured":"Roy, N., Merrill, R.M., Gray, S.D., Smith, E.M.: Voice disorders in the general population: prevalence, risk factors, and occupational impact. The Laryngoscope (2005)","DOI":"10.1097\/01.mlg.0000179174.32345.41"},{"key":"40_CR41","doi-asserted-by":"publisher","unstructured":"Saenz-Lechon, N., godino llorente, J., Osma-Ruiz, V., Blanco-Velasco, M., Cruz-Roldan, F.: Automatic assessment of voice quality according to the grbas scale. In: Conference Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 1, 2478\u20132481 (2006). https:\/\/doi.org\/10.1109\/IEMBS.2006.260603","DOI":"10.1109\/IEMBS.2006.260603"},{"issue":"9","key":"40_CR42","first-page":"3003","volume":"2","author":"L Salhi","year":"2008","unstructured":"Salhi, L., Talbi, M., Cherif, A.: Voice disorders identification using hybrid approach: wavelet analysis and multilayer neural networks. Int. J. Electr. Comput. Eng. 2(9), 3003\u20133012 (2008)","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"40_CR43","doi-asserted-by":"crossref","unstructured":"Spantideas, N., Drosou, E., Karatsis, A., Assimakopoulos, D.: Voice disorders in the general Greek population and in patients with laryngopharyngeal reflux. prevalence and risk factors. J. Voice (2015)","DOI":"10.1016\/j.jvoice.2014.08.006"},{"key":"40_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"40_CR45","doi-asserted-by":"crossref","unstructured":"Vieira, H., Costa, N., Sousa, T., Reis, S., Coelho, L.: Voice-based classification of amyotrophic lateral sclerosis: where are we and where are we going? A systematic review. Neurodegenerative Diseases (2020)","DOI":"10.1159\/000506259"},{"key":"40_CR46","doi-asserted-by":"publisher","unstructured":"Xie, X., Cai, H., Li, C., Ding, F.: A voice disease detection method based on MFCCS and shallow CNN (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.08708","DOI":"10.48550\/arXiv.2304.08708"},{"key":"40_CR47","doi-asserted-by":"crossref","unstructured":"Yang, Y., Panagopoulou, A., Zhou, S., Jin, D., Callison-Burch, C., Yatskar, M.: Language in a bottle: language model guided concept bottlenecks for interpretable image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19187\u201319197 (2023)","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"40_CR48","unstructured":"Zarlenga, M.E., et al.: Concept embedding models: beyond the accuracy-explainability trade-off (2022). https:\/\/arxiv.org\/abs\/2209.09056"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-19105-2_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:15:34Z","timestamp":1778364934000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-19105-2_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032191045","9783032191052"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-19105-2_40","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Authors have no competing interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}